skills/yayplanet-ryan/orca/orca-cli/Gen Agent Trust Hub

orca-cli

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a procedure for locating and executing the local orca CLI tool. It includes environment-specific logic to select the appropriate binary (checking for ORCA_CLI_COMMAND, ORCA_DEV_REPO_ROOT, or fallback to orca-ide / orca) to ensure compatibility and avoid conflicts with system tools like the GNOME Orca screen reader.- [PROMPT_INJECTION]: The skill implements a dynamic instruction loading pattern where the agent is instructed to run ORCA skills get orca-cli to retrieve the version-matched usage guide at runtime. This allows the skill to stay synchronized with the binary but relies on the binary providing safe instructional content.
  • Ingestion points: Output of the command ORCA skills get orca-cli (SKILL.md).
  • Boundary markers: No explicit boundary markers or ignore-instructions warnings are provided in the stub for the dynamic output.
  • Capability inventory: The tool facilitates management of worktrees, terminal sessions, automations, and an embedded browser (SKILL.md).
  • Sanitization: No validation or sanitization is performed on the output returned by the tool before the agent processes it as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:52 PM
Security Audit — agent-trust-hub — orca-cli